Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    polite phrases and expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows certain punctuation or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    actions and statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.53
    BibitemShut
    -0.49
     educate
    -0.47
    ∭
    -0.46
    Ausbildung
    -0.44
    oluted
    -0.44
     standoff
    -0.44
    TagMode
    -0.43
     Bollywood
    -0.43
     trainings
    -0.43
    POSITIVE LOGITS
    RectangleBorder
    0.37
     senhora
    0.36
    /***/
    0.35
    InsertCommand
    0.35
    setPointSize
    0.34
    ParallelGroup
    0.33
     Ferro
    0.33
    държа
    0.33
     sketch
    0.32
    #+#
    0.32
    Act Density 0.372%

    No Known Activations